Method for making space map and moving robot
An image of a space in which a mobile robot travels may be captured, and, in the case in which personal information is included in the captured image, the image including the personal information may be covered with a specific color such that the personal information is not visible, and the image may be replaced with an image including no personal information. As a result, it is possible to prevent the personal information from being exposed. In order to determine whether personal information is included in an image and to replace the image including the personal information with an image including no personal information, an object detection neural network and a frame prediction neural network may be used. In addition, input and output of an image may be performed in an Internet of Things (IoT) environment using a 5G network.
1. A spatial map information generation method performed by a processor, the spatial map information generation method comprising:
receiving a plurality of image frames of a space;
discriminating a first image frame comprising personal information from the image frames;
processing the first image frame so that the personal information is not displayed; and
storing a map of the space generated using the image frames comprising a result of processing the first image frame,
wherein the discriminating comprises determining whether at least one of an image of a face of an individual or an image comprising identification (ID) information is included in the image frame based on a personal information identification neural network.
2. The spatial map information generation method according to claim 1 , wherein the processing comprises filling the image of the face of the individual or the image comprising the identification (ID) information in the first image frame comprising at least one of the image of the face of the individual or the image comprising the identification information with a specific color in order to hide the personal information.
3. The spatial map information generation method according to claim 1 , wherein
the personal information comprises person information, and
the spatial map information generation method further comprises identifying a subject through facial recognition based on the personal information identification neural network.
4. The spatial map information generation method according to claim 1 , wherein the processing comprises filling the first image frame with a specific color.
5. A spatial map information generation method performed by a processor, the spatial map information generation method comprising:
receiving a plurality of image frames of a space;
discriminating a first image frame comprising personal information from the image frames;
processing the first image frame so that the personal information is not displayed; and
storing a map of the space generated using the image frames comprising a result of processing the first image frame, wherein
the processing comprises replacing the first image frame with an alternative first image frame, and
the alternative first image frame is an image predicted based on an image frame before the first image frame and an image frame after the first image frame using a frame prediction neural network.
6. A spatial map information generation method performed by a processor, the spatial map information generation method comprising:
receiving a plurality of image frames of a space;
discriminating a first image frame comprising personal information from the image frames;
processing the first image frame so that the personal information is not displayed; and
storing a map of the space generated using the image frames comprising a result of processing the first image frame,
wherein the spatial map information generation method further comprises:
after the processing,
storing the image frames in a buffer memory;
transmitting the image frames stored in the buffer memory to an external server in a case in which the image frames stored in the buffer memory exceed a capacity of the buffer memory; and
resetting the buffer memory.
7. A mobile robot configured to generate spatial map information, the mobile robot comprising:
one or more processors; and
a memory connected to the one or more processors,
wherein the memory stores a command configured to, when executed by the one or more processors, cause the one or more processors to:
receive a plurality of image frames of a space;
discriminate a first image frame comprising personal information from the image frames;
process the first image frame so that the personal information is not displayed; and
store a map of the space generated using the image frames comprising a result of processing the first image frame,
wherein the memory stores a command configured to cause the one or more processors to determine whether at least one of an image of a face of an individual or an image comprising identification (ID) information is included in the image frame based on a personal information identification neural network.
8. The mobile robot according to claim 7 , wherein the memory stores a command configured to cause the one or more processors to fill the image of the face of the individual or the image comprising the identification (ID) information in the first image frame comprising at least one of the image of the face of the individual or the image comprising the identification information with a specific color in order to hide the personal information.
9. The mobile robot according to claim 7 , wherein
the personal information comprises person information, and
the memory stores a command configured to cause the one or more processors to identify a subject through facial recognition based on the personal information identification neural network.
10. The mobile robot according to claim 7 , wherein the memory stores a command configured to cause the one or more processors to fill the first image frame with a specific color.
11. The mobile robot according to claim 10 , wherein the memory stores a command configured to cause the one or more processors to:
replace the first image frame with an alternative first image frame; and
predict the alternative first image frame based on an image frame before the first image frame and an image frame after the first image frame using a frame prediction neural network.
12. The mobile robot according to claim 7 , wherein the memory stores a command configured to cause the one or more processors to:
store the image frames in a buffer memory;
transmit the image frames stored in the buffer memory to an external server in a case in which the image frames stored in the buffer memory exceed a capacity of the buffer memory; and
reset the buffer memory.
13. A mobile robot configured to generate spatial map information, the mobile robot comprising:
a main body;
a driver configured to move the main body;
an image capturer configured to capture an image of a space in which the main body is moved by the driver;
a memory configured to store a plurality of image frames of the space captured by the image capturer; and
a processor configured to, upon identifying personal information in a first image frame comprising the personal information, among the image frames, process the first image frame so that the personal information is not displayed and to store a map of the space generated using the image frames comprising a result of processing the first image frame,
wherein the processor is configured to determine whether at least one of an image of a face of an individual or an image comprising identification (ID) information is included in the image frame based on a personal information identification neural network.
14. The mobile robot according to claim 13 , wherein the processor is configured to fill the image of the face of the individual or the image comprising the identification (ID) information in the first image frame comprising at least one of the image of the face of the individual or the image comprising the identification information with a specific color in order to hide the personal information.
15. The mobile robot according to claim 13 , wherein
the personal information comprises person information, and
the processor is configured to identify a subject through facial recognition based on the personal information identification neural network.
16. The mobile robot according to claim 13 , further comprising:
a buffer memory configured to store the image frames comprising the result of processing the first image frame and to transmit the stored image frames comprising the result of processing the first image frame to an external server in a case in which the image frames stored in the buffer memory exceed a capacity of the buffer memory.